Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling

• URL: http://arxiv.org/abs/2605.31283v1
• Date: Fri, 29 May 2026 13:14:43 GMT
• Title: Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling
• Abstract summary: SHELLS is an efficient feed-forward framework for 3D head reconstruction in dense semantic correspondence from multi-view images.<n>It reduces median registration error by 21% to 29% with a 3.5x inference speedup.<n>Our model is trained exclusively on synthetic data yet generalizes effectively to real-world captures.
• Score: 15.24889101682807
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present SHELLS (Semantic Head Estimation via Layered Local Sampling), an efficient feed-forward framework for 3D head reconstruction in dense semantic correspondence from multi-view images. Existing methods typically refine vertices independently via localized feature volumes. This approach couples memory-intensive feature sampling to mesh resolution, which limits scalability for dense topologies (> 10k vertices) and introduces surface noise. In contrast, SHELLS decouples feature extraction from mesh resolution via a hierarchical sampling strategy. We extract multi-view features using a DINOv2 backbone with LoRA adaptation, projectively sample a sparse global feature cloud, and predict an intermediate coarse mesh. This coarse prior guides the construction of layered, surface-aware sampling shells that serve as a discrete search space for the final reconstruction. SHELLS maintains surface consistency while using 88% less inference GPU memory (2.4GB vs. 20GB) than volumetric baselines. It reduces median registration error by 21% to 29% with a 3.5x inference speedup (0.08s vs. 0.29s) for 18k-vertex meshes. Notably, our model is trained exclusively on synthetic data yet generalizes effectively to real-world captures, eliminating the need for the costly, pre-registered multi-view datasets common in prior work.

Related papers

• SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision [10.62097148325093]
  Mesh subdivision is a fundamental operation for converting coarse, editable meshes into high-resolution surfaces.<n>We present SubdivAR, a neural mesh subdivision framework based on our proposed Mesh Autoregressive Representation (MAR)<n>MAR arranges meshes at different subdivision levels into an ordered scale sequence, reformulating subdivision as autoregressive next-scale prediction.
  arXiv  Detail & Related papers  (2026-06-25T14:24:03Z)
• Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction [9.96771578356719]
  Existing approaches rely on increasingly complex network architectures to regress depth maps.<n>We propose a multilevel conditional random field (CRF) model built upon the Swin Transformer backbone.<n>Our method achieves state-of-the-art performance, reducing Abs Rel to 0.088 ($-$7.4%) and RMSE to 0.316 ($-$5.4%) on NYU Depth v2, while attaining near-perfect threshold accuracy.
  arXiv  Detail & Related papers  (2026-04-03T07:59:26Z)
• Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence [78.1406635199656]
  Holi-Spatial is the first fully automated, large-scale, spatially-aware multimodal dataset constructed from raw video inputs without human intervention.<n>Holi-Spatial-4M is the first large-scale, high-quality 3D semantic dataset, containing 12K optimized 3DGS scenes, 1.3M 2D masks, 320K 3D bounding boxes, 320K instance captions, 1.2M 3D grounding instances, and 1.2M spatial QA pairs.
  arXiv  Detail & Related papers  (2026-03-08T14:49:20Z)
• Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface [49.742538510885]
  We propose Faithful Contouring, a voxelized representation that achieves near-lossless fidelity in 3D meshes.<n>The proposed method also shows flexibility and improvement for existing representation.
  arXiv  Detail & Related papers  (2025-11-06T03:56:12Z)
• Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes [59.17785932398617]
  High-quality view synthesis relies on volume rendering, splatting, or surface rendering.<n>We present a novel representation for real-time view synthesis where the number of sampling locations is small and bounded.<n>We achieve this by representing objects as semi-transparent multi-layer meshes rendered in a fixed order.
  arXiv  Detail & Related papers  (2024-09-04T07:18:26Z)
• C2F2NeUS: Cascade Cost Frustum Fusion for High Fidelity and Generalizable Neural Surface Reconstruction [12.621233209149953]
  We introduce a novel integration scheme that combines the multi-view stereo with neural signed distance function representations. Our method reconstructs robust surfaces and outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-16T17:56:16Z)
• Learning Neural Parametric Head Models [7.679586286000453]
  We propose a novel 3D morphable model for complete human heads based on hybrid neural fields. We capture a person's identity in a canonical space as a signed distance field (SDF), and model facial expressions with a neural deformation field. Our representation achieves high-fidelity local detail by introducing an ensemble of local fields centered around facial anchor points.
  arXiv  Detail & Related papers  (2022-12-06T05:24:42Z)
• BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling [60.257912103351394]
  We develop a new point cloud upsampling pipeline called BIMS-PU. We decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors. We show that our method achieves superior results to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-06-25T13:13:37Z)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)
• Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking [54.58791377183574]
  Our novel hybrid recurrent multi-view stereo net consists of two core modules: 1) a light DRENet (Dense Reception Expanded) module to extract dense feature maps of original size with multi-scale context information, 2) a HU-LSTM (Hybrid U-LSTM) to regularize 3D matching volume into predicted depth map. Our method exhibits competitive performance to the state-of-the-art method while dramatically reduces memory consumption, which costs only $19.4%$ of R-MVSNet memory consumption.
  arXiv  Detail & Related papers  (2020-07-21T14:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.